community pool / model answer

Qwen3.8-27B-IU4-Kairic-Edge

chat · jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

66.9 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Ryzen AI Max 395 128GB4-bit66.9 tok/smeasured-- GB32,768llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.